A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences
Statistics Theory
2011-06-01 v1 Statistics Theory
Abstract
We consider a Kullback-Leibler-based algorithm for the stochastic multi-armed bandit problem in the case of distributions with finite supports (not necessarily known beforehand), whose asymptotic regret matches the lower bound of \cite{Burnetas96}. Our contribution is to provide a finite-time analysis of this algorithm; we get bounds whose main terms are smaller than the ones of previously known algorithms with finite-time analyses (like UCB-type algorithms).
Keywords
Cite
@article{arxiv.1105.5820,
title = {A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences},
author = {Odalric-Ambrym Maillard and Rémi Munos and Gilles Stoltz},
journal= {arXiv preprint arXiv:1105.5820},
year = {2011}
}